OpenNERO: a game platform for AI research and education
作者： Igor V. Karpov , Risto Miikkulainen , John Sheblak
DOI:
关键词:
摘要: OpenNERO is an open source game platform designed for AI research. The software package combines features commonly available in modern engines (such as 3D graphics, physics simulation, audio rendering, networked play, and a powerful scripting interface) with easy to use API tools defining machine learning tasks, environments, agents. Flexibility ease of the system are demonstrated by following process creating from scratch. scalability tested through implementation existing NERO using new tools.
参考文章(3)
Michael Bowling, Johannes Fürnkranz, Thore Graepel, Ron Musick, Machine learning and games Machine Learning. ,vol. 63, pp. 211- 215 ,(2006) , 10.1007/S10994-006-8919-X
David W. Aha, Matthew Molineaux, TIELT: a testbed for gaming environments national conference on artificial intelligence. pp. 1690- 1691 ,(2005)
Kenneth O. Stanley and Bobby D. Bryant and Risto Miikkulainen, Evolving Neural Network Agents in the NERO Video Game ,(2005)